Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    job

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "));↵
    -0.07
     AR
    -0.06
    _restore
    -0.06
    confirmed
    -0.06
    ağa
    -0.06
    nothing
    -0.06
    ecký
    -0.06
    .;.;.;.;
    -0.06
    唯一
    -0.06
     burgers
    -0.06
    POSITIVE LOGITS
     Universal
    0.07
     लड
    0.06
     reveal
    0.06
    rack
    0.06
     rect
    0.06
     della
    0.06
     可
    0.06
     IGNORE
    0.06
     proposing
    0.06
     PDT
    0.06
    Act Density 0.015%

    No Known Activations